Graph Convolutional Network (ConvGNN)

From GM-RKB
(Redirected from GCN)
Jump to navigation Jump to search

A Graph Convolutional Network (ConvGNN) is a Graph Neural Network that is based on a Convolutional Neural Network.



References

2020a

2020 AComprehensiveSurveyonGraphNeur Fig1a.png 2020 AComprehensiveSurveyonGraphNeur Fig1b.png
(a) 2D Convolution. Analogous to a graph, each pixel in an image is taken as a node where neighbors are determined by the filter size. The 2D convolution takes the weighted average of pixel values of the red node along with its neighbors. The neighbors of a node are ordered and have a fixed size. (b) Graph Convolution. To get a hidden representation of the red node, one simple solution of the graph convolutional operation is to take the average value of the node features of the red node along with its neighbors. Different from image data, the neighbors of a node are unordered and variable in size.
Figure 1: 2D Convolution vs. Graph Convolution.

2020b

2019

2018a

2018b

2018c

2017

2017 SemiSupervisedClassificationwit Fig1.png
Figure 1: Left: Schematic depiction of multi-layer Graph Convolutional Network (GCN) for semi-supervised learning with $C$ input channels and $F$ feature maps in the output layer. The graph structure (edges shown as black lines) is shared over layers, labels are denoted by $Y_i$. Right: t-SNE (Maaten & Hinton, 2008) visualization of hidden layer activations of a two-layer GCN trained on the Cora dataset (Sen et al., 2008) using 5% of labels. Colors denote document class.